lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge conflicts

Browse Source
This commit is contained in:
BlankCheng
2024-03-06 21:34:58 +08:00
parent 5ebd080237 d748a77c63
commit 7e41955eb7
41 changed files with 2250 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
evaluation_examples/examples/multi_apps/185f29bd-5da0-40a6-b69c-ba7f4e0324ef.json Normal file
View File

@@ -0,0 +1,96 @@
{
"id": "185f29bd-5da0-40a6-b69c-ba7f4e0324ef",
"snapshot": "libreoffice_calc",
"instruction": "Transfer the data from our 'Employee Performance Evaluation Summary' Excel sheet into our standardized PDF evaluation forms. Each employee's evaluation data should be accurately filled into the designated fields of the PDF form. It's crucial that the final PDF documents retain a uniform and professional look, ready for distribution to our staff or for filing purposes. Furthermore, please ensure that each PDF file is named according to the employee's name as it appears in the Excel document. This will greatly streamline our evaluation process and enhance our efficiency in managing employee performance records. Oh, use \"√\" as mark on characters.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/Employee Performance Evaluation Summary.xlsx",
"url": "https://drive.google.com/uc?id=1uOzi66bzO_WUnoS4Oqsodrd7_YPLatEk&export=download"
},
{
"path": "/home/user/Desktop/review_template.pdf",
"url": "https://drive.google.com/uc?id=1YJ4RPGFUuS48tBh31gBerA16JSMw498w&export=download"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/Employee Performance Evaluation Summary.xlsx"
}
},
{
"type": "sleep",
"parameters": {
"seconds": 2
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/review_template.pdf"
}
}
],
"trajectory": "trajectories/185f29bd-5da0-40a6-b69c-ba7f4e0324ef",
"related_apps": [
"libreoffice_calc",
"os",
"pdf"
],
"evaluator": {
"func": "compare_pdfs",
"result": {
"type": "cloud_file",
"path": [
"https://drive.google.com/uc?id=1kZM90nA1krRmV9ug5_BBe8VlrZRVLiLK&export=download",
"https://drive.google.com/uc?id=1zyLzYYThwyit9ciXpfNfPFlBomolOauY&export=download",
"https://drive.google.com/uc?id=1gMT7JBftuymajMAO5rwksORpeVq3uGmH&export=download",
"https://drive.google.com/uc?id=1x0DdtUSZyBifl1tGIWlWKn255WusJeR4&export=download",
"https://drive.google.com/uc?id=1UAcG32WO8XCXElcanjGwbSpJwFuyOkts&export=download",
"https://drive.google.com/uc?id=1PRgryg7Y5evKnDG2LPtAttVp9qAf5VyZ&export=download",
"https://drive.google.com/uc?id=1JxEDriCS2W7BQLdkIgxu_WFCRa9ib4D7&export=download"
],
"dest": [
"Alex Lee_Gold.pdf",
"David Wilson_Gold.pdf",
"Emily Johnson_Gold.pdf",
"John Doe_Gold.pdf",
"Linda Green_Gold.pdf",
"Michael Brown_Gold.pdf",
"Sophia Carter_Gold.pdf"
],
"multi": true,
"gives": [0,1,2,3,4,5,6]
},
"expected": {
"type": "vm_file",
"path": [
"/home/user/Desktop/Alex Lee.pdf",
"/home/user/Desktop/David Wilson.pdf",
"/home/user/Desktop/Emily Johnson.pdf",
"/home/user/Desktop/John Doe.pdf",
"/home/user/Desktop/Linda Green.pdf",
"/home/user/Desktop/Michael Brown.pdf",
"/home/user/Desktop/Sophia Carter.pdf"
],
"dest": [
"Alex Lee.pdf",
"David Wilson.pdf",
"Emily Johnson.pdf",
"John Doe.pdf",
"Linda Green.pdf",
"Michael Brown.pdf",
"Sophia Carter.pdf"
],
"multi": true,
"gives": [0,1,2,3,4,5,6]
}
}
}

58
evaluation_examples/examples/multi_apps/20236825-b5df-46e7-89bf-62e1d640a897.json Normal file
View File

@@ -0,0 +1,58 @@
{
"id": "20236825-b5df-46e7-89bf-62e1d640a897",
"snapshot": "vscode",
"instruction": "I am coding on my algorithm practice. The doc \"bubble_Sort_tutorial.docx\" is the document for it. Help me finish the function 'bubbleSort' in 'bubbleSort.py' on the Desktop save the output in 'res.txt' on Desktop.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1AQtZ8Hrf7WtyUtaHMtDN-UErKRXnW64d&export=download&authuser=0&confirm=t&uuid=bf7f2b4b-ecf9-4260-b74e-db0cd40b58ca&at=APZUnTVimJzbmwJ8-4E1lq9ipJf_:1709624149129",
"path": "/home/user/Desktop/bubbleSort.zip"
},
{
"url": "https://drive.usercontent.google.com/download?id=168ZHCnK6v5PEZ8G5M25ZUW9fICk4OlfE&export=download&authuser=0&confirm=t&uuid=3642df08-dc40-4d37-93a0-8532e3012fb0&at=APZUnTUP1OTlq0kIgqcj7YSWw6MB:1709622592489",
"path": "/home/user/Desktop/Bubble_Sort_tutorial.docx"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"/bin/bash",
"-c",
"unzip /home/user/Desktop/bubbleSort.zip -d /home/user/Desktop/ && rm -rf /home/user/Desktop/bubbleSort.zip"
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/Bubble_Sort_tutorial.docx"
}
}
],
"trajectory": "trajectories/20236825-b5df-46e7-89bf-62e1d640a897",
"related_apps": [
"vscode",
"libreoffice_writer",
"os"
],
"evaluator": {
"func": "compare_text_file",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1g2Trt9oxQyW_sx8aIztFA0zNsE4yNw2x&export=download&authuser=0&confirm=t&uuid=342751c4-54f1-4760-9326-e7388845ded0&at=APZUnTV5BcbaxIZrDglWbs84Oxln:1709623697315",
"dest": "res.txt"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/res.txt",
"dest": "res.txt"
}
}
}

69
evaluation_examples/examples/multi_apps/227d2f97-562b-4ccb-ae47-a5ec9e142fbb.json Normal file
View File

@@ -0,0 +1,69 @@
{
"id": "227d2f97-562b-4ccb-ae47-a5ec9e142fbb",
"snapshot": "gimp",
"instruction": "I have my .xcf file saved on Desktop. Could you help me copy the image and paste it into a Libreoffice Writer file? Save it as 'image.docx' on the Desktop.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/QTdHniCqfJbBLJe3L3nijU-1200-80.xcf",
"url": "https://drive.usercontent.google.com/download?id=1BGoDOu9bYIG7Twj5dVTxRIWDUgWzzDtP&export=download&authuser=0&confirm=t&uuid=235d1bb2-37a0-4d96-82bf-a87f31d03cb4&at=APZUnTX53EdR1stASFS3OH5luAtB:1709617456061"
}
]
}
}
],
"trajectory": "trajectories/227d2f97-562b-4ccb-ae47-a5ec9e142fbb",
"related_apps": [
"libreoffice_writer",
"gimp",
"os"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "image.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey(\"ctrl\", \"s\"); time.sleep(0.5);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 1.0
}
}
],
"func": "compare_docx_images",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/image.docx",
"dest": "image.docx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=11kWQc1XFEqcIMuW0-NnZRSdv1199OmVI&export=download&authuser=0&confirm=t&uuid=694676fd-1ac9-4501-8acf-f48018494c7f&at=APZUnTV-koL51ka5dHum_HpGywv_:1709618406292",
"dest": "image.docx"
}
}
}

108
evaluation_examples/examples/multi_apps/22a4636f-8179-4357-8e87-d1743ece1f81.json Normal file
View File

@@ -0,0 +1,108 @@
{
"id": "22a4636f-8179-4357-8e87-d1743ece1f81",
"snapshot": "chrome",
"instruction": "Please help me convert the file \"Meeting-Agenda.docx\" to a pdf file and upload to the folder 'meetings' in my google drive.",
"source": "https://marketplace.uipath.com/listings/merge-pdfs-from-gmail-email-attachments-and-upload-to-gogle-drive",
"config": [
{
"type": "googledrive",
"parameters": {
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"operation": [
"delete",
"mkdirs"
],
"args": [
{
"query": "title = 'Meeting-Agenda.docx' or title = 'Meeting-Agenda.pdf'",
"trash": false
},
{
"path": [
"meetings"
]
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://news.google.com",
"https://x.com",
"https://www.deepl.com"
]
}
},
{
"type": "login",
"parameters": {
"settings_file": "evaluation_examples/settings/google/settings.json",
"platform": "googledrive"
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=17fkMG4guromDzAHNCzzJieZHa2nJDBpc&export=download&authuser=0&confirm=t",
"path": "/home/user/Desktop/Meeting-Agenda.docx"
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--writer",
"/home/user/Desktop/Meeting-Agenda.docx"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer",
"chrome"
],
"evaluator": {
"func": "compare_pdfs",
"result": {
"type": "googledrive_file",
"settings_file": "evaluation_examples/settings/googledrive/settings.yml",
"path": [
"meetings",
"Meeting-Agenda.pdf"
],
"dest": "Meeting-Agenda.pdf"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1wHWQ6mTJcNLtrL83GrUPzxx2HeOC4L8T&export=download&authuser=0&confirm=t",
"dest": "gold-Meeting-Agenda.pdf"
}
}
}

67
evaluation_examples/examples/multi_apps/236833a3-5704-47fc-888c-4f298f09f799.json Normal file
View File

@@ -0,0 +1,67 @@
{
"id": "236833a3-5704-47fc-888c-4f298f09f799",
"snapshot": "chrome",
"instruction": "Find daily papers on Huggingface and take down all the titles, authors and the abstracts of papers on 1st March, 2024 in the doc file 'paper_reading_2024_03_01.docx' on desktop. Each paragraph (split by empty lines) conforms to the following format:\nTitle: xxx\nAuthors: xxx, xxx, xxx\nAbstract: xxxxxxxx.\nArxiv PDF: https://xxxx.pdf",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://huggingface.co/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--writer"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"libreoffice_writer"
],
"evaluator": {
"func": "compare_docx_files",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/paper_reading_2024_03_01.docx",
"dest": "paper_reading_2024_03_01.docx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1TUTihXD93bIlekuYy_44fmXAhI1KVol4&export=download&authuser=0&confirm=t",
"dest": "gold_paper_reading_2024_03_01.docx"
},
"options": {
"ignore_blanks": true,
"ignore_case": true,
"ignore_order": true
}
}
}

102
evaluation_examples/examples/multi_apps/2c1ebcd7-9c6d-4c9a-afad-900e381ecd5e.json Normal file
View File

@@ -0,0 +1,102 @@
{
"id": "2c1ebcd7-9c6d-4c9a-afad-900e381ecd5e",
"snapshot": "libreoffice_calc",
"instruction": "Could you please take a moment to review the 'case study' file located within the 'student work' folder? I'm particularly interested in ensuring that the references section at the end of the document adheres to the APA 7th edition formatting guidelines. If it turns out that the current formatting does not align with APA 7 standards, I would greatly appreciate your assistance in making the necessary adjustments to comply with those guidelines. ",
"source": "authors",
"config": [
{
"type": "command",
"parameters": {
"command": [
"mkdir",
"-p",
"/home/user/Desktop/students work/",
"/home/user/Desktop/Lec powerpoint/",
"/home/user/Desktop/Grammar test/",
"/home/user/Desktop/Grammar rules PDF/",
"/home/user/Desktop/FDI/"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/students work/Zheng He .docx",
"url": "https://drive.google.com/uc?id=1wI4141LAthnY5m6qcCUaGgDooe4wiTgz&export=download"
},
{
"path": "/home/user/Desktop/students work/The literature reviews of weekly readings.docx",
"url": "https://drive.google.com/uc?id=18zoZCNtP-wTkxXp2FhH3O_NdLZKVMPIr&export=download"
},
{
"path": "/home/user/Desktop/students work/The British Justice System.docx",
"url": "https://drive.google.com/uc?id=1z3YHSN4CvC5kN1AwTWB_-plRS4p5GAch&export=download"
},
{
"path": "/home/user/Desktop/students work/quiz2.docx",
"url": "https://drive.google.com/uc?id=1R5Bii_kvnv_fZVXV-6DMt6Hgq-1gXMo1&export=download"
},
{
"path": "/home/user/Desktop/students work/quiz.docx",
"url": "https://drive.google.com/uc?id=1PvlGMVX7YkricrjoPRe0e5VQlHeozRPD&export=download"
},
{
"path": "/home/user/Desktop/students work/Q1&2&3.docx",
"url": "https://drive.google.com/uc?id=1kLQ3lnba6p9lqikHhKDdbqrYagHnZWU_&export=download"
},
{
"path": "/home/user/Desktop/students work/Photo Ethics in Journalism.docx",
"url": "https://drive.google.com/uc?id=1V6nG6HP_9Kb5KBCRTpaGsRTdPxnJSmRm&export=download"
},
{
"path": "/home/user/Desktop/students work/cassie.docx",
"url": "https://drive.google.com/uc?id=1cW9TGJy56vossXxDsdnutPyCbR70af7M&export=download"
},
{
"path": "/home/user/Desktop/students work/case study.docx",
"url": "https://drive.google.com/uc?id=11GzpoZvp4qnL2ukXdpbhH-a3zOIHhtDx&export=download"
},
{
"path": "/home/user/Desktop/Grammar rules PDF/irregularrules02.pdf",
"url": "https://drive.google.com/uc?id=1Eln9ehX6y6Df2-S_Hp7Ao1teKRu6I1Tg&export=download"
},
{
"path": "/home/user/Desktop/Grammar rules PDF/irregularrules01.pdf",
"url": "https://drive.google.com/uc?id=1krdEEdNWvTwMKZU14QtI_xc2lCFVeVcl&export=download"
},
{
"path": "/home/user/Desktop/Grammar rules PDF/fragrules.pdf",
"url": "https://drive.google.com/uc?id=1IXyI2KeiXsuh6XV2LelcmhZ2PDh_dBQf&export=download"
},
{
"path": "/home/user/Desktop/Grammar rules PDF/csfsrules.pdf",
"url": "https://drive.google.com/uc?id=1ernwGGrjhYNoHVNAevdb2qNKQ0I5n3RP&export=download"
},
{
"path": "/home/user/Desktop/Public Lecture Teaching Plan.docx",
"url": "https://drive.google.com/uc?id=1ywfVFTEbiSkypZpzLjLmq_ppSbQIC8s8&export=download"
},
{
"path": "/home/user/Desktop/Course Timetable.xlsx",
"url": "https://drive.google.com/uc?id=1NGtahknRq_kXsXlw0tRQ1_CZp9SljoVg&export=download"
}
]
}
}
],
"trajectory": "trajectories/2c1ebcd7-9c6d-4c9a-afad-900e381ecd5e",
"related_apps": [
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

49
evaluation_examples/examples/multi_apps/337d318b-aa07-4f4f-b763-89d9a2dd013f.json Normal file
View File

@@ -0,0 +1,49 @@
{
"id": "337d318b-aa07-4f4f-b763-89d9a2dd013f",
"snapshot": "libreoffice_calc",
"instruction": "Cross-check the invoices with the bank statements and identify any discrepancies. Then pull out the invoices that don't match the statements and put them in the \"problematic\" folder.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/invoice TII-20220301-90.pdf",
"url": "https://drive.google.com/uc?id=13y1Dkh9dJUaWeMSk6pg_UY-R7K4bhAJM&export=download"
},
{
"path": "/home/user/Desktop/Invoice # GES-20220215-82.pdf",
"url": "https://drive.google.com/uc?id=1zZYJQVpbGmqT_eH0x9Z5O7WoIFrQo3sN&export=download"
},
{
"path": "/home/user/Desktop/Invoice # 243729.pdf",
"url": "https://drive.google.com/uc?id=1a7fnWpsAdFQkFWl2BqAA_gTwlZ6nvGAx&export=download"
},
{
"path": "/home/user/Desktop/Bank-Statement.pdf",
"url": "https://drive.google.com/uc?id=1-KS6p0aip56iPmH4okhXZhLgqVwrcjfw&export=download"
}
]
}
}
],
"trajectory": "trajectories/337d318b-aa07-4f4f-b763-89d9a2dd013f",
"related_apps": [
"os",
"pdf"
],
"evaluator": {
"func": "compare_pdfs",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/problematic/Invoice # 243729.pdf",
"dest": "Invoice # 243729.pdf"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1a7fnWpsAdFQkFWl2BqAA_gTwlZ6nvGAx&export=download",
"dest": "Invoice # 243729 Gold.pdf"
}
}
}

26
evaluation_examples/examples/multi_apps/3a93cae4-ad3e-403e-8c12-65303b271818.json Normal file
View File

@@ -0,0 +1,26 @@
{
"id": "3a93cae4-ad3e-403e-8c12-65303b271818",
"snapshot": "libreoffice_calc",
"instruction": "Could you please add a two-hour lecture slot to my weekly course timetable, scheduled for every Wednesday at 12 PM? It seems I accidentally omitted that when setting up my schedule. I'd appreciate you taking care of that for me. Thanks!",
"source": "authors",
"config": [
],
"trajectory": "trajectories/3a93cae4-ad3e-403e-8c12-65303b271818",
"related_apps": [
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

147
evaluation_examples/examples/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b.json Normal file
View File

@@ -0,0 +1,147 @@
{
"id": "415ef462-bed3-493a-ac36-ca8c6d23bf1b",
"snapshot": "thunderbird",
"instruction": "Save the AWS invoice of December from the email. I have moved that email to local \"Bills\" folder. Save it to the my receipts folder. Keep the file name pattern and update a record to my tally book.",
"source": "authors",
"config": [
{
"type": "execute",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Documents/Finance/receipts", "/home/user/Documents/Projects"]
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf", "url": "https://drive.google.com/uc?id=1azRFXf4A7fvW0S7r9upHvleMEi-92hHM&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf", "url": "https://drive.google.com/uc?id=1x-lpHm8U4U7uRPZ74-9wq9KzW2R55ln1&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf", "url": "https://drive.google.com/uc?id=1pcrgV9G6NO4ekMEQBiupwXtq6mmke7b_&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf", "url": "https://drive.google.com/uc?id=1JzbCK_nIY8X_3QZjnkzTtb-cRoq9zNT-&export=download"},
{"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf", "url": "https://drive.google.com/uc?id=1QzWjNzvNosG_yQr7VVonvYb3cUYF5f3u&export=download"},
{"path": "/home/user/Documents/Finance/tally_book.xlsx", "url": "https://drive.google.com/uc?id=13yuLhBPmouoWR-DybfgaIbWUOxbY_jhL&export=download"},
{"path": "/home/user/.projects.tar.xz", "url": "https://drive.google.com/uc?id=1oJcxpjqF474Wm16i1aZc8DlCEfAvc4t_&export=download"},
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", "/home/user/.projects.tar.xz", "-C", "/home/user/Documents/Projects"]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": ["thunderbird"]
}
}
],
"trajectory": "trajectories/415ef462-bed3-493a-ac36-ca8c6d23bf1b",
"related_apps": ["thunderbird", "libreoffice_calc", "os"],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "tally_book.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/.aws-invoice-2312.pdf", "url": "https://drive.google.com/uc?id=1RqbulzKG_HeYb1GZmLABOzlohlFg02UU&export=download"}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["diff", ".aws-invoice-2312.pdf", "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf"],
"stdout": "diff.out"
}
}
],
"func": ["compare_table", "check_list"],
"result": [
{
"type": "vm_file",
"path": "/home/user/Documents/Finance/tally_book.xlsx",
"dest": "tally_book.xlsx"
},
{
"type": "cache_file",
"path": "diff.out"
}
],
"expected": [
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1x8m-korGI1PhJm8PAQVTlWYKneK4WKvn&export=download",
"dest": "tally_book_gt.xlsx"
},
{
"type": "rule",
"rules": {
"unexpect": [
".+"
]
}
}
],
"options": [
{
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
},
{}
]
}
}

116
evaluation_examples/examples/multi_apps/5990457f-2adb-467b-a4af-5c857c92d762.json Normal file
View File

@@ -0,0 +1,116 @@
{
"id": "5990457f-2adb-467b-a4af-5c857c92d762",
"snapshot": "chrome",
"instruction": "Append one entry of AI researcher Yann LeCun from Google Scholar into an existing table researchers.xlsx.",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://arxiv.org/abs/2005.14165",
"https://wallhaven.cc/"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EbQ75SHLthiZCBqCJtO0fLXJZcKrNler&export=download&authuser=0&confirm=t",
"path": "/home/user/Desktop/researchers.xlsx"
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"nautilus",
"/home/user/Desktop"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"libreoffice_calc"
],
"evaluator": {
"func": "literal_match",
"result": {
"type": "content_from_vm_file",
"path": "/home/user/Desktop/researchers.xlsx",
"file_type": "xlsx",
"file_content": "last_row"
},
"expected": {
"type": "info_from_website",
"url": "https://scholar.google.com/citations?user=WLN3QrAAAAAJ&hl=en",
"infos": [
{
"action": "inner_text",
"selector": "#gsc_prf_in"
},
{
"action": "inner_text",
"selector": "#gsc_rsb_st > tbody > tr:nth-child(1) > td:nth-child(2)"
},
{
"action": "inner_text",
"selector": "#gsc_rsb_st > tbody > tr:nth-child(2) > td:nth-child(2)"
},
{
"action": "inner_text",
"selector": "#gsc_rsb_st > tbody > tr:nth-child(3) > td:nth-child(2)"
},
{
"action": "inner_text",
"selector": "#gsc_a_b > tr:nth-child(1) > td.gsc_a_t > a"
},
{
"action": "click_and_attribute",
"selector": [
"#gsc_a_b > tr:nth-child(1) > td.gsc_a_t > a",
"#gsc_oci_title_gg > div:nth-child(1) > a"
],
"attribute": "href"
}
],
"backups": [
"Yann LeCun",
"345074",
"147",
"372",
"Deep learning",
"https://creativecoding.soe.ucsc.edu/courses/cs523/slides/week3/DeepLearning_LeCun.pdf"
]
},
"options": {
"type": "list",
"ignore_case": true
}
}
}

110
evaluation_examples/examples/multi_apps/67890eb6-6ce5-4c00-9e3d-fb4972699b06.json Normal file
View File

@@ -0,0 +1,110 @@
{
"id": "67890eb6-6ce5-4c00-9e3d-fb4972699b06",
"snapshot": "libreoffice_calc",
"instruction": "I am an NLP researcher. Check out the best long paper awards of ACL from 2019 to 2022 and record the 'title', 'year', 'author list' and 'PDF link' into table best_awards_acl.xslx on the desktop. Separate authors only by commas, use offical aclanthology urls not arxiv, and sort rows by years in descending orders.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.google.com/uc?export=download&id=1v5DgViUgAL771kBWy-qBddVGyjGmgFhK",
"path": "/home/user/Desktop/best_awards_acl.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/best_awards_acl.xlsx"
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://aclanthology.org/"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_calc",
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "best_awards_acl.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/best_awards_acl.xlsx",
"dest": "best_awards_acl.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=17ORdOPl3sZGk3s4Wm0vESgImKZjdZBqX&export=download&authuser=0&confirm=t",
"dest": "gold_best_awards_acl.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

48
evaluation_examples/examples/multi_apps/767a3271-56db-4745-ac5d-846ef05e6fe5.json
View File

@@ -1,27 +1,25 @@
{
"id": "767a3271-56db-4745-ac5d-846ef05e6fe5",
"snapshot": "libreoffice_calc",
"instruction": "Hey there! I've been swamped with emails lately, and I'm trying to get organized. I'm part of a local community group, and we've been receiving a lot of emails about different events and volunteer opportunities. I need to sort through these emails and pull out specific information to keep track of everything. Could you help me extract details from emails that mention 'volunteer opportunities' and organize them into a spreadsheet? I'm looking for the event name, date, location, and contact person's email. It would be a huge help if we could have this info neatly laid out so we can easily see what's coming up and who to contact. Thanks a bunch!",
"source": "authors",
"config": [
],
"trajectory": "trajectories/767a3271-56db-4745-ac5d-846ef05e6fe5",
"related_apps": [
"thunderbird",
"libreoffice_calc"
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
"id": "767a3271-56db-4745-ac5d-846ef05e6fe5",
"snapshot": "libreoffice_calc",
"instruction": "Hey there! I've been swamped with emails lately, and I'm trying to get organized. I'm part of a local community group, and we've been receiving a lot of emails about different events and volunteer opportunities. I need to sort through these emails and pull out specific information to keep track of everything. Could you help me extract details from emails that mention 'volunteer opportunities' and organize them into a spreadsheet? I'm looking for the event name, date, location, and contact person's email. It would be a huge help if we could have this info neatly laid out so we can easily see what's coming up and who to contact. Thanks a bunch!",
"source": "authors",
"config": [
{
}
],
"trajectory": "trajectories/767a3271-56db-4745-ac5d-846ef05e6fe5",
"related_apps": [
"thunderbird",
"libreoffice_calc"
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

89
evaluation_examples/examples/multi_apps/778efd0a-153f-4842-9214-f05fc176b877.json Normal file
View File

@@ -0,0 +1,89 @@
{
"id": "778efd0a-153f-4842-9214-f05fc176b877",
"snapshot": "vlc",
"instruction": "I'm using libreoffice impress to write slideshows. I found that the video being played by VLC media player had a good soundtrack. Please extract the audio to planet.wav and use it as background music for this slideshow.",
"source": "https://researchguides.case.edu/c.php?g=1286426",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1I-ArULOnZzlGkS9UyIuE8Dyuyus27iZt&export=download&authuser=0&confirm=t",
"path": "/home/user/Desktop/Minimalist_Business_Slides.pptx"
},
{
"url": "https://drive.usercontent.google.com/download?id=1HiW-PokIfWRyRvLwlkiVKKNCB2h2bcx7&export=download&authuser=0&confirm=t",
"path": "/home/user/Desktop/planet.mp4"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/Minimalist_Business_Slides.pptx"
}
},
{
"type": "launch",
"parameters": {
"command": [
"vlc",
"--repeat",
"/home/user/Desktop/planet.mp4"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_impress",
"vlc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Minimalist_Business_Slides.pptx - LibreOffice Impress",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_audios",
"result": {
"type": "audio_in_slide",
"ppt_file_path": "/home/user/Desktop/Minimalist_Business_Slides.pptx",
"slide_index": 0,
"dest": "planet.wav"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1F_iBPLgVg-2g1LQ5rxKyCrFa9UitZ9yn&export=download&authuser=0&confirm=t",
"dest": "gold_planet.wav"
}
}
}

89
evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json Normal file
View File

@@ -0,0 +1,89 @@
{
"id": "82e3c869-49f6-4305-a7ce-f3e64a0618e7",
"snapshot": "libreoffice_calc",
"instruction": "Please sift through the folder with all the event photos taken by our photographer. I need you to extract the photos featuring the presenters and place them in a separate folder named 'presenter'. Then, compress this folder into a zip file so I can easily share it with others later.",
"source": "authors",
"config": [
{
"type": "command",
"parameters": {
"command": [
"mkdir",
"-p",
"/home/user/Desktop/IDS LLM seminar/"
]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00659.jpg",
"url": "https://drive.google.com/uc?id=1NjnSab2aEtJytYajM9FqeXsLm4ItxTsJ&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00657.jpg",
"url": "https://drive.google.com/uc?id=1untYr5vS_wCVd3-5cfdUegBBILT4tHzF&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00574.jpg",
"url": "https://drive.google.com/uc?id=1V3g4z2QhIHx48LbeaNx31nMosxYPgtzY&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00554.jpg",
"url": "https://drive.google.com/uc?id=1DNz3iZmNk6-dazqXilOFkRpgUahU57zd&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00495.jpg",
"url": "https://drive.google.com/uc?id=1_crKe2tdI4Kjg0Xop8vHo7yN9KACJTJF&export=download"
},
{
"path": "/home/user/Desktop/IDS LLM seminar/DSC00454.jpg",
"url": "https://drive.google.com/uc?id=1t9L7fVQVxjovTQufetlogulIctn7DF_L&export=download"
}
]
}
}
],
"trajectory": "trajectories/82e3c869-49f6-4305-a7ce-f3e64a0618e7",
"related_apps": [
"os",
"image"
],
"evaluator": {
"func": "compare_image_list",
"result": {
"type": "vm_file",
"path": [
"/home/user/Desktop/presenter/DSC00657.jpg",
"/home/user/Desktop/presenter/DSC00574.jpg",
"/home/user/Desktop/presenter/DSC00554.jpg",
"/home/user/Desktop/presenter/DSC00495.jpg"
],
"dest": [
"DSC00657.jpg",
"DSC00574.jpg",
"DSC00554.jpg",
"DSC00495.jpg"
],
"multi": "true"
},
"expected": {
"type": "cloud_file",
"path": [
"https://drive.google.com/uc?id=1untYr5vS_wCVd3-5cfdUegBBILT4tHzF&export=download",
"https://drive.google.com/uc?id=1V3g4z2QhIHx48LbeaNx31nMosxYPgtzY&export=download",
"https://drive.google.com/uc?id=1DNz3iZmNk6-dazqXilOFkRpgUahU57zd&export=download",
"https://drive.google.com/uc?id=1_crKe2tdI4Kjg0Xop8vHo7yN9KACJTJF&export=download"
],
"dest": [
"DSC00657_gold.jpg",
"DSC00574_gold.jpg",
"DSC00554_gold.jpg",
"DSC00495_gold.jpg"
],
"multi": "true"
}
}
}

47
evaluation_examples/examples/multi_apps/8df7e444-8e06-4f93-8a1a-c5c974269d82.json Normal file
View File

@@ -0,0 +1,47 @@
{
"id": "8df7e444-8e06-4f93-8a1a-c5c974269d82",
"snapshot": "libreoffice_writer",
"instruction": "In the \"reminder.docx\" on Desktop is the submission instruction of our essay work. My essay is saved as docx file in /home/user. Please help me prepare the files for submission as required. ",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1wrCJd2f0xYnrHcj6KDzCe96X9JsN3VI3&export=download&authuser=0&confirm=t&uuid=277cb94d-1981-4f4d-b1ba-bceac8146001&at=APZUnTWKU5DBnr_6-_ZlEdsvhpCz:1709633482673",
"path": "/home/user/Recruitment_and_retention_of_health_professionals_across_Europe.docx"
},
{
"url": "https://drive.usercontent.google.com/download?id=1vzawJthEhQHcK4cUF0W9QT4zaFywO6aH&export=download&authuser=0&confirm=t&uuid=0fbb6a50-f9c1-44d2-b430-3af738d5fadc&at=APZUnTWyfv-N5f-EjnF8ob-VfCsD:1709633450986",
"path": "/home/user/Desktop/reminder.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/reminder.docx"
}
}
],
"trajectory": "trajectories/8df7e444-8e06-4f93-8a1a-c5c974269d82",
"related_apps": [
"libreoffice_writer",
"os"
],
"evaluator": {
"func": "compare_zip_files",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1IKRu-dMFP4Aqzq5-4TOmOWVci0qvC27K&export=download&authuser=0&confirm=t&uuid=e2dabad2-5648-4bc3-a40f-f008089cd613&at=APZUnTVh5JD5nT3EvutwHIaSnJAT:1709633945616",
"dest": "Recruitment_and_retention_of_health_professionals_across_Europe.zip"
},
"result": {
"type": "vm_file",
"path": "/home/user/Recruitment_and_retention_of_health_professionals_across_Europe.zip",
"dest": "Recruitment_and_retention_of_health_professionals_across_Europe.zip"
}
}
}

241
evaluation_examples/examples/multi_apps/8e116af7-7db7-4e35-a68b-b0939c066c78.json Normal file
View File

@@ -0,0 +1,241 @@
{
"id": "8e116af7-7db7-4e35-a68b-b0939c066c78",
"snapshot": "libreoffice_calc",
"instruction": "Please update my bookkeeping sheet with the recent transactions from the provided folder, detailing my expenses over the past few days.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/my_bookkeeping.xlsx",
"url": "https://drive.google.com/uc?id=1QOSpTZPFzFZeC0tng4Gfws544LFln836&export=download"
},
{
"path": "/home/user/Desktop/receipt_0.jpeg",
"url": "https://drive.google.com/uc?id=1b0BRc-BzXObVCUEonJfRbDsrgxZugj3U&export=download"
},
{
"path": "/home/user/Desktop/receipt_1.jpg",
"url": "https://drive.google.com/uc?id=1S-JBDqwEf7Z_JXDItK_F4BOHgScTjlyN&export=download"
},
{
"path": "/home/user/Desktop/receipt_2.jpg",
"url": "https://drive.google.com/uc?id=1Ys2abZi9_0y8sxuj2vCbC0OhjC6YdrC-&export=download"
},
{
"path": "/home/user/Desktop/receipt_3.pdf",
"url": "https://drive.google.com/uc?id=1sKvBbGDpmUkv891xTqX7w5dtEvchQahd&export=download"
},
{
"path": "/home/user/Desktop/receipt_4.jpg",
"url": "https://drive.google.com/uc?id=1kW7xH5bc2jRaKGDKHDrgSehTrPgkyzkc&export=download"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/my_bookkeeping.xlsx"
}
}
],
"trajectory": "trajectories/8e116af7-7db7-4e35-a68b-b0939c066c78",
"related_apps": [
"libreoffice_calc",
"os",
"image",
"pdf"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "my_bookkeeping.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 1.0
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/my_bookkeeping.xlsx",
"dest": "my_bookkeeping.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1ygEDdVlkf2ZyqMxJ_ktqo9G_g--rc6co&export=download",
"dest": "my_bookkeeping_gold.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_fuzzy",
"sheet_idx0": "RNSheet1",
"sheet_idx1": "ENSheet1",
"rules": [
{
"range": [
"A1:A8",
"B1:B8",
"C1:C8",
"D1:D8",
"E1:E8"
],
"type": "exact_match"
}
]
},
{
"type": "sheet_fuzzy",
"sheet_idx0": "RNSheet1",
"sheet_idx1": "ENSheet1",
"rules": [
{
"range": [
"C9:C13"
],
"type": "exact_match",
"ignore_case": true
}
]
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "D9",
"props": {
"value": {
"method": "approx:0.1",
"ref": -186.93
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "D10",
"props": {
"value": {
"method": "approx:0.1",
"ref": -3670
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "D11",
"props": {
"value": {
"method": "approx:0.1",
"ref": -5.7
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "D12",
"props": {
"value": {
"method": "approx:0.1",
"ref": -154.06
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "D13",
"props": {
"value": {
"method": "approx:0.1",
"ref": -8.1
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "E9",
"props": {
"value": {
"method": "approx:0.1",
"ref": 603.07
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "E10",
"props": {
"value": {
"method": "approx:0.1",
"ref": -3066.93
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "E11",
"props": {
"value": {
"method": "approx:0.1",
"ref": -3072.63
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "E12",
"props": {
"value": {
"method": "approx:0.1",
"ref": -3226.69
}
}
},
{
"type": "check_cell",
"sheet_idx": 0,
"coordinate": "E13",
"props": {
"value": {
"method": "approx:0.1",
"ref": -3234.79
}
}
}
]
}
}
}

47
evaluation_examples/examples/multi_apps/a503b07f-9119-456b-b75d-f5146737d24f.json Normal file
View File

@@ -0,0 +1,47 @@
{
"id": "a503b07f-9119-456b-b75d-f5146737d24f",
"snapshot": "os",
"instruction": "I am preparing for my paper reading report. Could you help me download this image at https://github.com/xlang-ai/OpenAgents/blob/main/pics/openagents_overview.png and convert it to PDF format. Save it as \"openagents_overview.pdf\" on desktop.",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/a503b07f-9119-456b-b75d-f5146737d24f",
"related_apps": [
"os",
"chrome",
"gimp",
"pdf"
],
"evaluator": {
"func": "compare_pdfs",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1gD1odFNuLT6TP6rpAv_hot86pKcI5wY1&export=download&authuser=0&confirm=t&uuid=9d17c689-95d3-45e4-b093-0165de4045b4&at=APZUnTV9SssKQCoYyYeVsi8e9zcX:1709649491796",
"dest": "openagents_overview.pdf"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/openagents_overview.pdf",
"dest": "openagents_overview.pdf"
}
}
}

85
evaluation_examples/examples/multi_apps/b337d106-053f-4d37-8da0-7f9c4043a66b.json Normal file
View File

@@ -0,0 +1,85 @@
{
"id": "b337d106-053f-4d37-8da0-7f9c4043a66b",
"snapshot": "os",
"instruction": "I've recently wanted to try using the Vim editor to edit code, but my Vim editor doesn't show relative line numbers by default. Please search the internet for a tutorial on how to display relative line numbers and make it the default setting for my local Vim.",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; time.sleep(0.5); pyautogui.click(960, 540); time.sleep(0.5); pyautogui.hotkey('ctrl', 'alt', 't'); time.sleep(0.5)"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Terminal"
}
}
],
"trajectory": "trajectories/b337d106-053f-4d37-8da0-7f9c4043a66b",
"related_apps": [
"os",
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1CyhWjUS2oov4Fzc0VRwTh6LiS2Qu-T_8&export=download&authuser=0&confirm=t&uuid=9d0e2c62-895c-4bb3-a057-30cae60329ed&at=APZUnTVngSwARjYsWSmhSyHAqwID:1709647023362",
"path": "eval.sh"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": "chmod +x eval.sh",
"shell": true
}
}
],
"func": "check_include_exclude",
"result": {
"type": "vm_command_line",
"command": "bash eval.sh",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"include": [
"The File Has Set Number!"
],
"exclude": []
}
}
}
}

2
evaluation_examples/examples/multi_apps/b5062e3e-641c-4e3a-907b-ac864d2e7652.json
View File

@@ -1,7 +1,7 @@
{
"id": "b5062e3e-641c-4e3a-907b-ac864d2e7652",
"snapshot": "libreoffice_calc",
"instruction": "I've got a mass of different categories of paper in PDF under folder \"~/Documents/Papers\". Please help me to extract the name, mail, and affiliation of the first author of all the papers and note them in an Excel table. The corresponding headers should be added in the table. Simply sort the authors by their full names ascendingly. The summary file should be saved as \"~/authors.xlsx\".",
"instruction": "I've got a mass of papers in PDF under folder \"~/Documents/Papers\". Please help me to extract the name, mail, and affiliation of the first author of all the papers and note them in an Excel table. The corresponding headers should be added in the table. Simply sort the authors by their full names ascendingly. The summary file should be saved as \"~/authors.xlsx\".",
"source": "authors",
"config": [
{

26
evaluation_examples/examples/multi_apps/d28853f4-500a-4749-b9dc-79c3576e759b.json Normal file
View File

@@ -0,0 +1,26 @@
{
"id": "d28853f4-500a-4749-b9dc-79c3576e759b",
"snapshot": "libreoffice_calc",
"instruction": "Hey there! So, I've got this bit of a situation and I'm hoping you can help me out. I've been working on gathering research for this big project at work, and I've ended up with a bunch of PDF files from various sources. Each PDF contains some really crucial information that I need, but here's the kicker - I need all of this info to be in one place where I can easily access and edit it, like in a Word document or a README file.\n\nThe PDFs are a mix of things - some are reports with statistics and findings, others are articles with key insights, and a few are just informational brochures with important dates and details. What I need is for someone to go through each PDF, extract all the relevant information, and then organize it into a single document. I'm talking about making sure that all the stats, insights, dates, and details from each PDF are neatly compiled, so I don't miss anything.\n\nAnd to make things a bit more complicated, some of these PDFs are scanned images of documents, so the text isn't directly selectable. I guess that means you might need to manually type out some parts or find a way to convert the images to text that can be copied.\n\nOnce everything's been compiled into this one document, could you save it as both a Word doc and a README file? I'd like to have it in these two formats so I can easily share it with my team and also have a version that's ready to be uploaded to our project's repository.\n\nOh, and could you make sure to organize the information by the source PDF? Like, maybe start each section with the title of the PDF or a brief description of its contents, followed by all the extracted info from that PDF. This way, it'll be easier for me and the team to trace back to the original sources if we need to.\n\nI know it's a lot to ask, but having all this information consolidated and organized is going to be a huge help for moving forward with the project. Thanks a bunch for helping me tackle this!",
"source": "authors",
"config": [
],
"trajectory": "trajectories/d28853f4-500a-4749-b9dc-79c3576e759b",
"related_apps": [
],
"evaluator": {
"postconfig": [],
"func": "",
"result": {
},
"expected": {
},
"options": {
}
}
}

101
evaluation_examples/examples/multi_apps/deec51c9-3b1e-4b9e-993c-4776f20e8bb2.json Normal file
View File

@@ -0,0 +1,101 @@
{
"id": "deec51c9-3b1e-4b9e-993c-4776f20e8bb2",
"snapshot": "libreoffice_calc",
"instruction": "Find a paper list of all the new foundation language models issued on 11st Oct. 2023 via arxiv daily, and organize it into the sheet I opened.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/Desktop/New Large Language Models.xlsx",
"url": "https://drive.google.com/uc?id=1NJFAUDzatd5TbBqXeCy3-ok4BWj-xayT&export=download"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/New Large Language Models.xlsx"
}
}
],
"trajectory": "trajectories/deec51c9-3b1e-4b9e-993c-4776f20e8bb2",
"related_apps": [
"libreoffice_calc",
"chrome",
"os"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "New Large Language Models.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 1.0
}
}
],
"func": "compare_table",
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/New Large Language Models.xlsx",
"dest": "New Large Language Models.xlsx"
},
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1BHOyjFo72b74YKWTqPMaoNvCzICkos-G&export=download",
"dest": "New Large Language Models Gold.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_fuzzy",
"sheet_idx0": "RNSheet1",
"sheet_idx1": "ENSheet1",
"rules": [
{
"range": [
"B2:B5",
"C2:C5"
],
"type": "exact_match"
},
{
"range": [
"A2:A5"
],
"type": "fuzzy_match",
"threshold": 90,
"ignore_case": true
}
]
}
]
}
}
}

59
evaluation_examples/examples/multi_apps/e1fc0df3-c8b9-4ee7-864c-d0b590d3aa56.json Normal file
View File

@@ -0,0 +1,59 @@
{
"id": "e1fc0df3-c8b9-4ee7-864c-d0b590d3aa56",
"snapshot": "libreoffice_writer",
"instruction": "Install LanguageTool extension for my LibreOffice",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": ["libreoffice", "--writer"]
}
}
],
"trajectory": "trajectories/e1fc0df3-c8b9-4ee7-864c-d0b590d3aa56",
"related_apps": ["chrome", "libreoffice", "os"],
"evaluator": {
"postconfig": [
{
"type": "command",
"parameters": {
"command": ["grep", "-nHr", "languagetool", "/home/user/.config/libreoffice/4/user/uno_packages/cache/uno_packages/"],
"stdout": "grep.out"
}
},
{
"type": "command",
"parameters": {
"command": ["apt", "list", "--installed"],
"stdout": "apt.out"
}
}
],
"func": ["check_list", "check_list"],
"result": [
{
"type": "cache_file",
"path": "grep.out"
},
{
"type": "cache_file",
"path": "apt.out"
}
],
"expected": [
{
"type": "rule",
"rules": {
"expect": ["org\\.openoffice\\.languagetool\\.oxt"]
}
},
{
"type": "rule",
"rules": {
"expect": ["openjdk-\\d+-(jre|jdk)"]
}
}
]
}
}

86
evaluation_examples/examples/multi_apps/e2392362-125e-4f76-a2ee-524b183a3412.json Normal file
View File

@@ -0,0 +1,86 @@
{
"id": "e2392362-125e-4f76-a2ee-524b183a3412",
"snapshot": "chrome",
"instruction": "I recently started using the famous personal academic homepage template from academicpages.github.io to build my own personal homepage, and I have cloned it to my local ~/Code/Website folder. According to an online tutorial, I can configure my name and contact information in the _config.yaml file. However, I am not familiar with the YAML file format. Please help me find the sections related to the name and contact information in this file and change them to “Test Account” and “Test@gmail.com”.",
"source": "authors",
"config": [
{
"type": "command",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Code/Website"]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"path": "/home/user/.tmp.tar.xz",
"url": "https://drive.google.com/uc?id=1ordb5kRSPDKgRi7nYQchn8hGt-INELML&export=download"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", ".tmp.tar.xz", "-C", "/home/user/Code/Website/"]
}
},
{
"type": "launch",
"parameters": {
"command": ["google-chrome", "--remote-debugging-port=1337"]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": ["https://academicpages.github.io/"]
}
}
],
"trajectory": "trajectories/e2392362-125e-4f76-a2ee-524b183a3412",
"related_apps": ["chrome", "os", "vscode"],
"evaluator": {
"func": "check_json",
"options": {"is_yaml": true},
"expected": {
"type": "rule",
"rules": {
"expect": [
{
"key": ["name"],
"method": "eq",
"ref": "Test Account"
},
{
"key": ["author", "name"],
"method": "eq",
"ref": "Test Account"
},
{
"key": ["author", "email"],
"method": "eq",
"ref": "Test@gmail.com"
}
]
}
},
"result": {
"type": "vm_file",
"path": "/home/user/Code/Website/academicpages.github.io/_config.yml",
"dest": "_config.yaml"
}
}
}

71
evaluation_examples/examples/multi_apps/f5c13cdd-205c-4719-a562-348ae5cd1d91.json Normal file
View File

@@ -0,0 +1,71 @@
{
"id": "f5c13cdd-205c-4719-a562-348ae5cd1d91",
"snapshot": "thunderbird",
"instruction": "Here is a table recording tuition payments in ~/Documents/Departments/finance. I have already composed an e-mail to remind people who haven't finished payment yet. Please help me to add their emails to the receiver field.",
"source": "authors",
"config": [
{
"type": "execute",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Documents/Departments/finance"]
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
},
{
"url": "https://drive.google.com/uc?id=1k0_69RKAx18bEX00EJXtWmSwdfNVP9NA&export=download",
"path": "/home/user/.payment-reminder-mail-body.html"
},
{
"url": "https://drive.google.com/uc?id=1nNc0NoOuP3Of0eGsKY-1kctg63vIjXl5&export=download",
"path": "/home/user/Documents/Departments/finance/tuition.xlsx"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": "/usr/bin/thunderbird -compose \"from='Anonym Tester <anonym-x2024@outlook.com>',subject='Reminder of Payment',body='$(cat /home/user/.payment-reminder-mail-body.html)'\"",
"shell": true
}
}
],
"trajectory": "trajectories/f5c13cdd-205c-4719-a562-348ae5cd1d91",
"related_apps": ["thunderbird", "os", "libreoffice_calc"],
"evaluator": {
"func": "check_accessibility_tree",
"result": {
"type": "accessibility_tree"
},
"expected": {
"type": "rule",
"rules": [
{"selectors": ["tool-bar[attr|id=MsgHeadersToolbar] label[attr|class=\"pill-label\"][name*=\"fox@someuniversity.edu\"]"]},
{"selectors": ["tool-bar[attr|id=MsgHeadersToolbar] label[attr|class=\"pill-label\"][name*=\"iron@someuniversity.edu\"]"]},
{"selectors": ["tool-bar[attr|id=MsgHeadersToolbar] label[attr|class=\"pill-label\"][name*=\"nancy@someuniversity.edu\"]"]},
{"selectors": ["tool-bar[attr|id=MsgHeadersToolbar] label[attr|class=\"pill-label\"][name*=\"stella@someuniversity.edu\"]"]}
]
}
}
}

31
evaluation_examples/examples/multi_apps/f8369178-fafe-40c2-adc4-b9b08a125456.json Normal file
View File

@@ -0,0 +1,31 @@
{
"id": "f8369178-fafe-40c2-adc4-b9b08a125456",
"snapshot": "chrome",
"instruction": "Help me to install Orchis theme from gnome-look.org and change to it for my GNOME desktop.",
"source": "https://itsfoss.com/install-switch-themes-gnome-shell",
"config": [],
"trajectory": "trajectories/f8369178-fafe-40c2-adc4-b9b08a125456",
"related_apps": ["chrome", "os"],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": ["gsettings", "get", "org.gnome.desktop.interface", "gtk-theme"],
"stdout": "gsettings.out"
}
}
],
"func": "check_list",
"result": {
"type": "cache_file",
"path": "gsettings.out"
},
"expected": {
"type": "rule",
"rules": {
"expect": ["Orchis"]
}
}
}
}

12
evaluation_examples/examples/thunderbird/12086550-11c0-466b-b367-1d9e75b3910e.json
View File

@@ -48,11 +48,13 @@
},
"expected": {
"type": "rule",
"rules": {
"selectors": [
"application[name=Thunderbird] page-tab-list[attr|id=\"tabmail-tabs\"]>page-tab[name=\"About Profiles\"]"
]
}
"rules": [
{
"selectors": [
"application[name=Thunderbird] page-tab-list[attr|id=\"tabmail-tabs\"]>page-tab[name=\"About Profiles\"]"
]
}
]
},
"func": "check_accessibility_tree"
}